static void predict(NdArray seq, FunctionStack model, int pre_length)
{
Ensure.Argument(model).NotNull();
Ensure.Argument(seq).NotNull();
Ensure.Argument(pre_length).GreaterThanOrEqualTo(0);
Real[] pre_input_seq = new Real[seq.Data.Length / 4];
if (pre_input_seq.Length < 1)
{
pre_input_seq = new Real[1];
}
Array.Copy(seq.Data, pre_input_seq, pre_input_seq.Length);
List <Real> input_seq = new List <Real>();
input_seq.AddRange(pre_input_seq);
List <Real> output_seq = new List <Real> {
input_seq[input_seq.Count - 1]
};
for (int i = 0; i < pre_length; i++)
{
Real future = predict_sequence(model, input_seq);
input_seq.RemoveAt(0);
input_seq.Add(future);
output_seq.Add(future);
}
foreach (var t in output_seq)
{
RILogManager.Default?.SendDebug(t.ToString());
}
RILogManager.Default?.SendDebug(seq.ToString());
}
public static void Run()
{
//Align Weight before and after splitting
Real[,] testWeightValues =
{
{ -0.02690255, 0.08830735, -0.02041466, -0.0431439, -0.07749002 },
{ -0.06963444, -0.03971611, 0.0597842, 0.08824182, -0.06649109 },
{ -0.04966073, -0.04697048, -0.02235234, -0.09396666, 0.073189 },
{ 0.06563969, 0.04446745, -0.07192299, 0.06784364, 0.09575776 },
{ 0.05012317, -0.08874852, -0.05977172, -0.05910181, -0.06009106 },
{ -0.05200623, -0.09679124, 0.02159978, -0.08058041, -0.01340541 },
{ -0.0254951, 0.09963084, 0.00936683, -0.08179696, 0.09604459 },
{ -0.0732494, 0.07253634, 0.05981455, -0.01007657, -0.02992892 },
{ -0.06818873, -0.02579817, 0.06767359, -0.03379837, -0.04880046 },
{ -0.06429326, -0.08964688, -0.0960066, -0.00286683, -0.05761427 },
{ -0.0454098, 0.07809167, -0.05030088, -0.02533244, -0.02322736 },
{ -0.00866754, -0.03614252, 0.05237325, 0.06478979, -0.03599609 },
{ -0.01789357, -0.04479434, -0.05765592, 0.03237658, -0.06403019 },
{ -0.02421552, 0.05533903, -0.08627617, 0.094624, 0.03319318 },
{ 0.02328842, -0.08234859, -0.07979888, 0.01439688, -0.03267198 },
{ -0.07128382, 0.08531934, 0.07180037, 0.04772871, -0.08938966 },
{ 0.09431138, 0.02094762, 0.04443646, 0.07653841, 0.02028433 },
{ 0.01844446, -0.08441339, 0.01957355, 0.04430714, -0.03080243 },
{ -0.0261334, -0.03794889, -0.00638074, 0.07278767, -0.02165155 },
{ 0.08390063, -0.03253863, 0.0311571, 0.08088892, -0.07267931 }
};
Real[][,] testJaggWeightValues =
{
new Real[, ] {
{ -0.02690255,0.08830735, -0.02041466, -0.0431439, -0.07749002 },
{ -0.06963444,-0.03971611, 0.0597842, 0.08824182, -0.06649109 },
{ -0.04966073,-0.04697048, -0.02235234, -0.09396666, 0.073189 },
{ 0.06563969,0.04446745, -0.07192299, 0.06784364, 0.09575776 },
{ 0.05012317, -0.08874852, -0.05977172, -0.05910181, -0.06009106 }
},
new Real[, ] {
{ -0.05200623,-0.09679124, 0.02159978, -0.08058041, -0.01340541 },
{ -0.0254951,0.09963084, 0.00936683, -0.08179696, 0.09604459 },
{ -0.0732494,0.07253634, 0.05981455, -0.01007657, -0.02992892 },
{ -0.06818873,-0.02579817, 0.06767359, -0.03379837, -0.04880046 },
{ -0.06429326, -0.08964688, -0.0960066, -0.00286683, -0.05761427 }
},
new Real[, ] {
{ -0.0454098,0.07809167, -0.05030088, -0.02533244, -0.02322736 },
{ -0.00866754,-0.03614252, 0.05237325, 0.06478979, -0.03599609 },
{ -0.01789357,-0.04479434, -0.05765592, 0.03237658, -0.06403019 },
{ -0.02421552,0.05533903, -0.08627617, 0.094624, 0.03319318 },
{ 0.02328842, -0.08234859, -0.07979888, 0.01439688, -0.03267198 }
},
new Real[, ] {
{ -0.07128382,0.08531934, 0.07180037, 0.04772871, -0.08938966 },
{ 0.09431138,0.02094762, 0.04443646, 0.07653841, 0.02028433 },
{ 0.01844446,-0.08441339, 0.01957355, 0.04430714, -0.03080243 },
{ -0.0261334,-0.03794889, -0.00638074, 0.07278767, -0.02165155 },
{ 0.08390063, -0.03253863, 0.0311571, 0.08088892, -0.07267931 }
}
};
Linear l0 = new Linear(true, 5, 20, initialW: testWeightValues, name: "l0");
Linear l1 = new Linear(true, 5, 5, initialW: testJaggWeightValues[0], name: "l1");
Linear l2 = new Linear(true, 5, 5, initialW: testJaggWeightValues[1], name: "l2");
Linear l3 = new Linear(true, 5, 5, initialW: testJaggWeightValues[2], name: "l3");
Linear l4 = new Linear(true, 5, 5, initialW: testJaggWeightValues[3], name: "l4");
l0.SetOptimizer(new SGD());
SGD sgd = new SGD();
l1.SetOptimizer(sgd);
l2.SetOptimizer(sgd);
l3.SetOptimizer(sgd);
l4.SetOptimizer(sgd);
//Input is equivalent, but Grad is added and it is divided
Real[] testValue = { 0.01618112, -0.08296648, -0.05545357, 0.00389254, -0.05727582 };
NdArray testInputValuesA = new NdArray(testValue);
NdArray testInputValuesB = new NdArray(testValue);
RILogManager.Default?.SendDebug("l0 for");
NdArray[] l0Result = l0.Forward(true, testInputValuesA);
RILogManager.Default?.SendDebug(l0Result.ToString());
RILogManager.Default?.SendDebug("l1 for");
NdArray[] l1Result = l1.Forward(true, testInputValuesB);
RILogManager.Default?.SendDebug(l1Result.ToString());
RILogManager.Default?.SendDebug("l2 for");
NdArray[] l2Result = l2.Forward(true, testInputValuesB);
RILogManager.Default?.SendDebug(l2Result.ToString());
RILogManager.Default?.SendDebug("l3 for");
NdArray[] l3Result = l3.Forward(true, testInputValuesB);
RILogManager.Default?.SendDebug(l3Result.ToString());
RILogManager.Default?.SendDebug("l4 for");
NdArray[] l4Result = l4.Forward(true, testInputValuesB);
RILogManager.Default?.SendDebug(l4Result.ToString());
//Create an appropriate Grad value
l0Result[0].Grad = new Real[]
{
-2.42022760e-02, 5.02482988e-04, 2.52015481e-04, 8.08797951e-04, -7.19293347e-03,
1.40045900e-04, 7.09874439e-05, 2.07651625e-04, 3.80124636e-02, -8.87162634e-04,
-4.64874669e-04, -1.40792923e-03, -4.12280299e-02, -3.36557830e-04, -1.50323089e-04,
-4.70047118e-04, 3.61101292e-02, -7.12957408e-04, -3.63163825e-04, -1.12809543e-03
};
l1Result[0].Grad = new Real[] { -2.42022760e-02, 5.02482988e-04, 2.52015481e-04, 8.08797951e-04, -7.19293347e-03 };
l2Result[0].Grad = new Real[] { 1.40045900e-04, 7.09874439e-05, 2.07651625e-04, 3.80124636e-02, -8.87162634e-04 };
l3Result[0].Grad = new Real[] { -4.64874669e-04, -1.40792923e-03, -4.12280299e-02, -3.36557830e-04, -1.50323089e-04 };
l4Result[0].Grad = new Real[] { -4.70047118e-04, 3.61101292e-02, -7.12957408e-04, -3.63163825e-04, -1.12809543e-03 };
//Backward
l0.Backward(true, l0Result);
l1.Backward(true, l1Result);
l2.Backward(true, l2Result);
l3.Backward(true, l3Result);
l4.Backward(true, l4Result);
RILogManager.Default?.SendDebug("l0 back");
RILogManager.Default?.SendDebug(testInputValuesA.ToString("Grad"));
RILogManager.Default?.SendDebug("l1-l4 sum back");
RILogManager.Default?.SendDebug(testInputValuesB.ToString("Grad"));
l0.Update(); //Although the format is irregular, since 10 contains SGD
sgd.Update(); // Use stochastic gradient descent as the optimizer
RILogManager.Default?.SendDebug("l0 Weight");
RILogManager.Default?.SendDebug(l0.Weight.ToString());
RILogManager.Default?.SendDebug("l1 Weight");
RILogManager.Default?.SendDebug(l1.Weight.ToString());
RILogManager.Default?.SendDebug("l0 Bias");
RILogManager.Default?.SendDebug(l0.Bias.ToString());
RILogManager.Default?.SendDebug("l1 Bias");
RILogManager.Default?.SendDebug(l1.Bias.ToString());
}
public void Shape(NdArray <int> array, string expSubstr)
{
Assert.Contains(expSubstr, array.ToString("S"));
}
public void ElementFormat(NdArray <int> array, string expected)
{
var actual = array.ToString("E(0000)");
Assert.Equal(expected, actual);
}
public void Basic(NdArray <int> array, string expected)
{
var actual = array.ToString();
Assert.Equal(expected, actual);
}
public static void Run()
{
//Weightを分割の前と後で揃える
Real[,] testWeightValues =
{
{ -0.02690255, 0.08830735, -0.02041466, -0.0431439, -0.07749002 },
{ -0.06963444, -0.03971611, 0.0597842, 0.08824182, -0.06649109 },
{ -0.04966073, -0.04697048, -0.02235234, -0.09396666, 0.073189 },
{ 0.06563969, 0.04446745, -0.07192299, 0.06784364, 0.09575776 },
{ 0.05012317, -0.08874852, -0.05977172, -0.05910181, -0.06009106 },
{ -0.05200623, -0.09679124, 0.02159978, -0.08058041, -0.01340541 },
{ -0.0254951, 0.09963084, 0.00936683, -0.08179696, 0.09604459 },
{ -0.0732494, 0.07253634, 0.05981455, -0.01007657, -0.02992892 },
{ -0.06818873, -0.02579817, 0.06767359, -0.03379837, -0.04880046 },
{ -0.06429326, -0.08964688, -0.0960066, -0.00286683, -0.05761427 },
{ -0.0454098, 0.07809167, -0.05030088, -0.02533244, -0.02322736 },
{ -0.00866754, -0.03614252, 0.05237325, 0.06478979, -0.03599609 },
{ -0.01789357, -0.04479434, -0.05765592, 0.03237658, -0.06403019 },
{ -0.02421552, 0.05533903, -0.08627617, 0.094624, 0.03319318 },
{ 0.02328842, -0.08234859, -0.07979888, 0.01439688, -0.03267198 },
{ -0.07128382, 0.08531934, 0.07180037, 0.04772871, -0.08938966 },
{ 0.09431138, 0.02094762, 0.04443646, 0.07653841, 0.02028433 },
{ 0.01844446, -0.08441339, 0.01957355, 0.04430714, -0.03080243 },
{ -0.0261334, -0.03794889, -0.00638074, 0.07278767, -0.02165155 },
{ 0.08390063, -0.03253863, 0.0311571, 0.08088892, -0.07267931 }
};
Real[][,] testJaggWeightValues =
{
new Real[, ] {
{ -0.02690255,0.08830735, -0.02041466, -0.0431439, -0.07749002 },
{ -0.06963444,-0.03971611, 0.0597842, 0.08824182, -0.06649109 },
{ -0.04966073,-0.04697048, -0.02235234, -0.09396666, 0.073189 },
{ 0.06563969,0.04446745, -0.07192299, 0.06784364, 0.09575776 },
{ 0.05012317, -0.08874852, -0.05977172, -0.05910181, -0.06009106 }
},
new Real[, ] {
{ -0.05200623,-0.09679124, 0.02159978, -0.08058041, -0.01340541 },
{ -0.0254951,0.09963084, 0.00936683, -0.08179696, 0.09604459 },
{ -0.0732494,0.07253634, 0.05981455, -0.01007657, -0.02992892 },
{ -0.06818873,-0.02579817, 0.06767359, -0.03379837, -0.04880046 },
{ -0.06429326, -0.08964688, -0.0960066, -0.00286683, -0.05761427 }
},
new Real[, ] {
{ -0.0454098,0.07809167, -0.05030088, -0.02533244, -0.02322736 },
{ -0.00866754,-0.03614252, 0.05237325, 0.06478979, -0.03599609 },
{ -0.01789357,-0.04479434, -0.05765592, 0.03237658, -0.06403019 },
{ -0.02421552,0.05533903, -0.08627617, 0.094624, 0.03319318 },
{ 0.02328842, -0.08234859, -0.07979888, 0.01439688, -0.03267198 }
},
new Real[, ] {
{ -0.07128382,0.08531934, 0.07180037, 0.04772871, -0.08938966 },
{ 0.09431138,0.02094762, 0.04443646, 0.07653841, 0.02028433 },
{ 0.01844446,-0.08441339, 0.01957355, 0.04430714, -0.03080243 },
{ -0.0261334,-0.03794889, -0.00638074, 0.07278767, -0.02165155 },
{ 0.08390063, -0.03253863, 0.0311571, 0.08088892, -0.07267931 }
}
};
Linear l0 = new Linear(5, 20, initialW: testWeightValues, name: "l0");
Linear l1 = new Linear(5, 5, initialW: testJaggWeightValues[0], name: "l1");
Linear l2 = new Linear(5, 5, initialW: testJaggWeightValues[1], name: "l2");
Linear l3 = new Linear(5, 5, initialW: testJaggWeightValues[2], name: "l3");
Linear l4 = new Linear(5, 5, initialW: testJaggWeightValues[3], name: "l4");
//FunctionにOptimizerを設定
l0.SetOptimizer(new SGD());
//OptimiserにFunctionを登録
SGD sgd = new SGD();
l1.SetOptimizer(sgd);
l2.SetOptimizer(sgd);
l3.SetOptimizer(sgd);
l4.SetOptimizer(sgd);
//入力は同値だがGradが加算されてしまうため分ける
Real[] testValue = { 0.01618112, -0.08296648, -0.05545357, 0.00389254, -0.05727582 };
NdArray testInputValuesA = new NdArray(testValue);
NdArray testInputValuesB = new NdArray(testValue);
Console.WriteLine("l0 for");
NdArray l0Result = l0.Forward(testInputValuesA)[0];
Console.WriteLine(l0Result);
Console.WriteLine("\nl1 for");
NdArray l1Result = l1.Forward(testInputValuesB)[0];
Console.WriteLine(l1Result);
Console.WriteLine("\nl2 for");
NdArray l2Result = l2.Forward(testInputValuesB)[0];
Console.WriteLine(l2Result);
Console.WriteLine("\nl3 for");
NdArray l3Result = l3.Forward(testInputValuesB)[0];
Console.WriteLine(l3Result);
Console.WriteLine("\nl4 for");
NdArray l4Result = l4.Forward(testInputValuesB)[0];
Console.WriteLine(l4Result);
Console.WriteLine();
//適当なGrad値をでっち上げる
l0Result.Grad = new Real[]
{
-2.42022760e-02, 5.02482988e-04, 2.52015481e-04, 8.08797951e-04, -7.19293347e-03,
1.40045900e-04, 7.09874439e-05, 2.07651625e-04, 3.80124636e-02, -8.87162634e-04,
-4.64874669e-04, -1.40792923e-03, -4.12280299e-02, -3.36557830e-04, -1.50323089e-04,
-4.70047118e-04, 3.61101292e-02, -7.12957408e-04, -3.63163825e-04, -1.12809543e-03
};
l1Result.Grad = new Real[] { -2.42022760e-02, 5.02482988e-04, 2.52015481e-04, 8.08797951e-04, -7.19293347e-03 };
l2Result.Grad = new Real[] { 1.40045900e-04, 7.09874439e-05, 2.07651625e-04, 3.80124636e-02, -8.87162634e-04 };
l3Result.Grad = new Real[] { -4.64874669e-04, -1.40792923e-03, -4.12280299e-02, -3.36557830e-04, -1.50323089e-04 };
l4Result.Grad = new Real[] { -4.70047118e-04, 3.61101292e-02, -7.12957408e-04, -3.63163825e-04, -1.12809543e-03 };
//Backwardを実行
l0.Backward(l0Result);
l1.Backward(l1Result);
l2.Backward(l2Result);
l3.Backward(l3Result);
l4.Backward(l4Result);
Console.WriteLine("\nl0 back");
Console.WriteLine(testInputValuesA.ToString("Grad"));
Console.WriteLine("\nl1-l4 sum back");
Console.WriteLine(testInputValuesB.ToString("Grad"));
l0.Update(); //書式が変則的だがl0はSGDを内包しているため
sgd.Update(); //こちらはOptimizerに関数を登録して使用している
Console.WriteLine("\nl0 Weight");
Console.WriteLine(l0.Weight);
Console.WriteLine("\nl1 Weight");
Console.WriteLine(l1.Weight);
Console.WriteLine("\nl0 Bias");
Console.WriteLine(l0.Bias);
Console.WriteLine("\nl1 Bias");
Console.WriteLine(l1.Bias);
}
public static void Run()
{
//Weightを分割の前と後で揃える
Real[,] testWeightValues = new Real[, ] {
{ -0.02690255f, 0.08830735f, -0.02041466f, -0.0431439f, -0.07749002f },
{ -0.06963444f, -0.03971611f, 0.0597842f, 0.08824182f, -0.06649109f },
{ -0.04966073f, -0.04697048f, -0.02235234f, -0.09396666f, 0.073189f },
{ 0.06563969f, 0.04446745f, -0.07192299f, 0.06784364f, 0.09575776f },
{ 0.05012317f, -0.08874852f, -0.05977172f, -0.05910181f, -0.06009106f },
{ -0.05200623f, -0.09679124f, 0.02159978f, -0.08058041f, -0.01340541f },
{ -0.0254951f, 0.09963084f, 0.00936683f, -0.08179696f, 0.09604459f },
{ -0.0732494f, 0.07253634f, 0.05981455f, -0.01007657f, -0.02992892f },
{ -0.06818873f, -0.02579817f, 0.06767359f, -0.03379837f, -0.04880046f },
{ -0.06429326f, -0.08964688f, -0.0960066f, -0.00286683f, -0.05761427f },
{ -0.0454098f, 0.07809167f, -0.05030088f, -0.02533244f, -0.02322736f },
{ -0.00866754f, -0.03614252f, 0.05237325f, 0.06478979f, -0.03599609f },
{ -0.01789357f, -0.04479434f, -0.05765592f, 0.03237658f, -0.06403019f },
{ -0.02421552f, 0.05533903f, -0.08627617f, 0.094624f, 0.03319318f },
{ 0.02328842f, -0.08234859f, -0.07979888f, 0.01439688f, -0.03267198f },
{ -0.07128382f, 0.08531934f, 0.07180037f, 0.04772871f, -0.08938966f },
{ 0.09431138f, 0.02094762f, 0.04443646f, 0.07653841f, 0.02028433f },
{ 0.01844446f, -0.08441339f, 0.01957355f, 0.04430714f, -0.03080243f },
{ -0.0261334f, -0.03794889f, -0.00638074f, 0.07278767f, -0.02165155f },
{ 0.08390063f, -0.03253863f, 0.0311571f, 0.08088892f, -0.07267931f }
};
Real[][,] testJaggWeightValues =
{
new Real[, ] {
{ -0.02690255f,0.08830735f, -0.02041466f, -0.0431439f, -0.07749002f },
{ -0.06963444f,-0.03971611f, 0.0597842f, 0.08824182f, -0.06649109f },
{ -0.04966073f,-0.04697048f, -0.02235234f, -0.09396666f, 0.073189f },
{ 0.06563969f,0.04446745f, -0.07192299f, 0.06784364f, 0.09575776f },
{ 0.05012317f, -0.08874852f, -0.05977172f, -0.05910181f, -0.06009106f }
},
new Real[, ] {
{ -0.05200623f,-0.09679124f, 0.02159978f, -0.08058041f, -0.01340541f },
{ -0.0254951f,0.09963084f, 0.00936683f, -0.08179696f, 0.09604459f },
{ -0.0732494f,0.07253634f, 0.05981455f, -0.01007657f, -0.02992892f },
{ -0.06818873f,-0.02579817f, 0.06767359f, -0.03379837f, -0.04880046f },
{ -0.06429326f, -0.08964688f, -0.0960066f, -0.00286683f, -0.05761427f }
},
new Real[, ] {
{ -0.0454098f,0.07809167f, -0.05030088f, -0.02533244f, -0.02322736f },
{ -0.00866754f,-0.03614252f, 0.05237325f, 0.06478979f, -0.03599609f },
{ -0.01789357f,-0.04479434f, -0.05765592f, 0.03237658f, -0.06403019f },
{ -0.02421552f,0.05533903f, -0.08627617f, 0.094624f, 0.03319318f },
{ 0.02328842f, -0.08234859f, -0.07979888f, 0.01439688f, -0.03267198f }
},
new Real[, ] {
{ -0.07128382f,0.08531934f, 0.07180037f, 0.04772871f, -0.08938966f },
{ 0.09431138f,0.02094762f, 0.04443646f, 0.07653841f, 0.02028433f },
{ 0.01844446f,-0.08441339f, 0.01957355f, 0.04430714f, -0.03080243f },
{ -0.0261334f,-0.03794889f, -0.00638074f, 0.07278767f, -0.02165155f },
{ 0.08390063f, -0.03253863f, 0.0311571f, 0.08088892f, -0.07267931f }
}
};
Linear <Real> l0 = new Linear <Real>(5, 20, initialW: testWeightValues, name: "l0");
Linear <Real> l1 = new Linear <Real>(5, 5, initialW: testJaggWeightValues[0], name: "l1");
Linear <Real> l2 = new Linear <Real>(5, 5, initialW: testJaggWeightValues[1], name: "l2");
Linear <Real> l3 = new Linear <Real>(5, 5, initialW: testJaggWeightValues[2], name: "l3");
Linear <Real> l4 = new Linear <Real>(5, 5, initialW: testJaggWeightValues[3], name: "l4");
//FunctionにOptimizerを設定
SGD <Real> sgd = new SGD <Real>();
sgd.SetUp(l0);
//OptimiserにFunctionを登録
SGD <Real> sgdSplit = new SGD <Real>();
sgdSplit.SetUp(l1);
sgdSplit.SetUp(l2);
sgdSplit.SetUp(l3);
sgdSplit.SetUp(l4);
//入力は同値だがGradが加算されてしまうため分ける
Real[] testValue = new Real[] { 0.01618112f, -0.08296648f, -0.05545357f, 0.00389254f, -0.05727582f };
NdArray <Real> testInputValuesA = new NdArray <Real>(testValue);
NdArray <Real> testInputValuesB = new NdArray <Real>(testValue);
Console.WriteLine("l0 for");
NdArray <Real> l0Result = l0.Forward(testInputValuesA)[0];
Console.WriteLine(l0Result);
Console.WriteLine("\nl1 for");
NdArray <Real> l1Result = l1.Forward(testInputValuesB)[0];
Console.WriteLine(l1Result);
Console.WriteLine("\nl2 for");
NdArray <Real> l2Result = l2.Forward(testInputValuesB)[0];
Console.WriteLine(l2Result);
Console.WriteLine("\nl3 for");
NdArray <Real> l3Result = l3.Forward(testInputValuesB)[0];
Console.WriteLine(l3Result);
Console.WriteLine("\nl4 for");
NdArray <Real> l4Result = l4.Forward(testInputValuesB)[0];
Console.WriteLine(l4Result);
Console.WriteLine();
//適当なGrad値をでっち上げる
l0Result.Grad = new Real[]
{
-2.42022760e-02f, 5.02482988e-04f, 2.52015481e-04f, 8.08797951e-04f, -7.19293347e-03f,
1.40045900e-04f, 7.09874439e-05f, 2.07651625e-04f, 3.80124636e-02f, -8.87162634e-04f,
-4.64874669e-04f, -1.40792923e-03f, -4.12280299e-02f, -3.36557830e-04f, -1.50323089e-04f,
-4.70047118e-04f, 3.61101292e-02f, -7.12957408e-04f, -3.63163825e-04f, -1.12809543e-03f
};
l1Result.Grad = new Real[] { -2.42022760e-02f, 5.02482988e-04f, 2.52015481e-04f, 8.08797951e-04f, -7.19293347e-03f };
l2Result.Grad = new Real[] { 1.40045900e-04f, 7.09874439e-05f, 2.07651625e-04f, 3.80124636e-02f, -8.87162634e-04f };
l3Result.Grad = new Real[] { -4.64874669e-04f, -1.40792923e-03f, -4.12280299e-02f, -3.36557830e-04f, -1.50323089e-04f };
l4Result.Grad = new Real[] { -4.70047118e-04f, 3.61101292e-02f, -7.12957408e-04f, -3.63163825e-04f, -1.12809543e-03f };
//Backwardを実行
l0.Backward(l0Result);
l1.Backward(l1Result);
l2.Backward(l2Result);
l3.Backward(l3Result);
l4.Backward(l4Result);
Console.WriteLine("\nl0 back");
Console.WriteLine(testInputValuesA.ToString("Grad"));
Console.WriteLine("\nl1-l4 sum back");
Console.WriteLine(testInputValuesB.ToString("Grad"));
sgd.Update();
sgdSplit.Update();
Console.WriteLine("\nl0 Weight");
Console.WriteLine(l0.Weight);
Console.WriteLine("\nl1 Weight");
Console.WriteLine(l1.Weight);
Console.WriteLine("\nl0 Bias");
Console.WriteLine(l0.Bias);
Console.WriteLine("\nl1 Bias");
Console.WriteLine(l1.Bias);
}
